Jun Hao Liew*
·
Hanshu Yan*
·
Jianfeng Zhang
·
Zhongcong Xu
·
Jiashi Feng
ByteDance Inc.
MagicEdit explicitly disentangles the learning of appearance and motion to achieve high-fidelity and temporally coherent video editing. It supports various editing applications, including video stylization, local editing, video-MagicMix and video outpainting.
For avatar-centric video generation and animation, please also check our latest work MagicAvatar!
If you find our work useful, please consider citing:
@inproceedings{liew2023magicedit,
author = {Liew, Jun Hao and Yan, Hanshu and Zhang, Jianfeng and Xu, Zhongcong and Feng, Jiashi},
title = {MagicEdit: High-Fidelity and Temporally Coherent Video Editing},
booktitle = {arXiv},
year = {2023}
}